Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning

• URL: http://arxiv.org/abs/2508.08165v1
• Date: Mon, 11 Aug 2025 16:41:04 GMT
• Title: Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning
• Authors: Yan Wang, Da-Wei Zhou, Han-Jia Ye,
• Abstract summary: We propose integrating Task-Specific and Universal Adapters (TUNA) in this paper.<n> Specifically, we train task-specific adapters to capture the most crucial features relevant to their respective tasks.<n>We leverage an adapter fusion strategy to construct a universal adapter, which encodes the most discriminative features shared across tasks.
• Score: 33.57130798344366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using additional lightweight modules such as adapters. However, incorrect module selection during inference hurts performance, and task-specific modules often overlook shared general knowledge, leading to errors on distinguishing between similar classes across tasks. To address the aforementioned challenges, we propose integrating Task-Specific and Universal Adapters (TUNA) in this paper. Specifically, we train task-specific adapters to capture the most crucial features relevant to their respective tasks and introduce an entropy-based selection mechanism to choose the most suitable adapter. Furthermore, we leverage an adapter fusion strategy to construct a universal adapter, which encodes the most discriminative features shared across tasks. We combine task-specific and universal adapter predictions to harness both specialized and general knowledge during inference. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of our approach. Code is available at: https://github.com/LAMDA-CL/ICCV2025-TUNA

Related papers

• CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning [8.81873424028249]
  Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes.<n>We propose a novel dual-adapter architecture combining textbftask-shared adapters to learn cross-task knowledge and textbftask-specific adapters to capture unique features of each new task.<n>We demonstrate CL-LoRA consistently achieves promising performance under multiple benchmarks with reduced training and inference computation.
  arXiv  Detail & Related papers  (2025-05-30T17:19:52Z)
• Adapter-Enhanced Semantic Prompting for Continual Learning [91.63494614012362]
  Continual learning (CL) enables models to adapt to evolving data streams.<n>Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge.<n>We propose a novel lightweight CL framework, which integrates prompt tuning and adapter techniques.
  arXiv  Detail & Related papers  (2024-12-15T06:14:55Z)
• MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair [5.006064616335817]
  Large Language Models (LLMs) have shown high capabilities in several software development-related tasks.<n> adapters offer a more efficient way to customize LLMs for particular needs.<n>Model (and adapter) merging have emerged as a technique to develop one model capable of multiple tasks.
  arXiv  Detail & Related papers  (2024-08-18T18:45:48Z)
• Task-Customized Mixture of Adapters for General Image Fusion [51.8742437521891]
  General image fusion aims at integrating important information from multi-source images. We propose a novel task-customized mixture of adapters (TC-MoA) for general image fusion, adaptively prompting various fusion tasks in a unified model.
  arXiv  Detail & Related papers  (2024-03-19T07:02:08Z)
• I2I: Initializing Adapters with Improvised Knowledge [15.452979531094567]
  Improvise for. I2LiI, a continual learning algorithm, initializes Adapters for incoming tasks by distilling. previously-learned tasks. I2I consistently achieves better task accuracy than independently-trained Adapters.
  arXiv  Detail & Related papers  (2023-04-04T23:51:48Z)
• Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters [59.82088750033897]
  We set up a Generalized FSCL (GFSCL) protocol involving both class- and domain-incremental situations. We find that common continual learning methods have poor generalization ability on unseen domains. In this way, we propose a rehearsal-free framework based on Vision Transformer (ViT) named Contrastive Mixture of Adapters (CMoA)
  arXiv  Detail & Related papers  (2023-02-12T15:18:14Z)
• Multi-Head Adapter Routing for Cross-Task Generalization [56.75667096355806]
  Polytropon learns an inventory of adapters and a routing function that selects a subset of adapters for each task during both pre-training and few-shot adaptation. We find that routing is most beneficial during multi-task pre-training rather than during few-shot adaptation.
  arXiv  Detail & Related papers  (2022-11-07T19:35:55Z)
• Adaptable Adapters [74.65986170056945]
  State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adaptable adapters contain different activation functions for different layers and different input data. We show that adaptable adapters achieve on-par performances with the standard adapter architecture.
  arXiv  Detail & Related papers  (2022-05-03T14:59:27Z)
• Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks [37.2958914602899]
  We show that we can learn adapter parameters for all layers and tasks by generating them using shared hypernetworks. Experiments on the well-known GLUE benchmark show improved performance in multi-task learning while adding only 0.29% parameters per task.
  arXiv  Detail & Related papers  (2021-06-08T16:16:40Z)
• AdapterHub: A Framework for Adapting Transformers [148.6877231725939]
  AdapterHub is a framework that allows dynamic "stitching-in" of pre-trained adapters for different tasks and languages. Our framework enables scalable and easy access to sharing of task-specific models.
  arXiv  Detail & Related papers  (2020-07-15T15:56:05Z)
• AdapterFusion: Non-Destructive Task Composition for Transfer Learning [104.9639614787314]
  Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks. We propose AdapterFusion, a new two stage learning algorithm that leverages knowledge from multiple tasks. We show that our approach outperforms traditional strategies such as full fine-tuning as well as multi-task learning.
  arXiv  Detail & Related papers  (2020-05-01T07:03:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.